Wayfair Tech Blog

Wayfair Tech Explains It All: Alex Pankhurst on Inbound/Outbound Fulfillment

Reliable outbound fulfillment, inventory replenishment, and positioning are all fundamental to creating an online purchase experience that delights our customers with rapid home delivery. As a result of our commitment to this reliability, we strive to offer one and two-day delivery times when possible, sharpen customer pricing, lower fulfillment costs, and increase sales through high in-stock levels paired with an exciting delivery experience. In this video, Senior Product Manager Alex Pankhurst will explain how Wayfair is heavily invested in building automated solutions in this space, including scaling our platforms as the complexities of our supply chain continue to grow.

Wayfair Tech Blog

Modeling Uplift Directly: Uplift Decision Tree with KL Divergence and Euclidean Distance as Splitting Criteria

Introduction

Wayfair Tech Blog

Wayfair Tech Explains It All: David Short on Formulaic Naming

Wayfair merchandisers currently spend thousands of hours each year manually naming the millions of products we sell. This unstructured data is costly to maintain and subject to human error as individuals currently update a free text field. With Formulaic Naming, Wayfair is transitioning to a structured solution for naming based on other questions we already ask our suppliers about their products. Once we have this structured information, we can pursue Dynamic Naming, where the product name will vary based on where the name is displayed and the customer who is viewing the product. This week, David Short, a Product Manager in Merchandising Systems at Wayfair, will discuss the work he's doing with Merchandising Engineering to automate this process.

Wayfair Tech Blog

Wayfair DS Explains It All: Anurag Syal on Projection Mapping in 3D

At Wayfair, we do everything we can to help our customers find exactly the products they need to furnish their homes in the style they envision. But creating all of the necessary elements to allow them to do that is not as easy as one might think. Right now, if an artist designs a new stylistic look for a home from scratch, it takes weeks before we actually get to introduce the products in the market to fit that look. Interestingly, it is not product manufacturing, but the creation of 3D models for these products that is the slowest and most expensive part of this process. There are a few key reasons for this; first of all, 3D models are required for product manufacturing, but 3D modeling software licenses and experience modelers are pricey and hard to come by. Secondly, to create a production quality 3D model (using a software like 3DS Max or Maya), 3D modelers need numerous 2D images of the product from various angles; given this requirement, you can imagine how costly a single rework or a minor change could be.

Wayfair Tech Blog

Open-Sourcing Our Internal Frontend Education Platform – Awesome Learning

When you walk into a company like Wayfair, it can feel overwhelming. There are more than 2,300 engineers across the organization. Every person you talk to seems smarter than the last.

Wayfair Tech Blog

Wayfair DS Explains It All: Lin Jia on Measuring Price Effects

Understanding price effects is of high importance to any business, but usually it's not easy to measure. To do this, Wayfair’s algorithms team has been designing modeling and experimental approaches so that we can disentangle the intricate web of causality. In this video, Wayfair Senior Data Scientist Lin Jia explains a couple of ways that we can measure price effects.

Wayfair Tech Blog

Wayfair DS Explains It All: Ilkay Yildiz on Learning From Comparisons

Stylistic preference is an important factor when a home goods customer is deciding which product to buy, but it is very difficult to identify and define. Although designers have established different style categories, labeling a scene as adhering to a particular style is a highly subjective task. Furthermore, customers often cannot verbalize their style preferences, but can identify their preferences by looking at images. Thus, it is crucial to show products in a room context that are tailored to a customer's taste.

Wayfair Tech Blog

Wayfair DS Explains It All: Samuel Yusuf on Collaborative Filtering

Wayfair sells over 10 million products on our website. This vast selection ensures that customers have numerous options when shopping for a particular item; but it also makes effective, personalized product recommendations of vital importance in helping our customers find products that are relevant to their interests. This week in Wayfair Data Science’s explainer series, Data Scientist Samuel Yusuf discusses the two main domains of collaborative filtering (memory based and model based) and how they can be applied to make predictions on a customer’s preference for a product.

Wayfair Tech Blog

Why Operations Engineering?

I love operations engineering, full stop. Focusing on this unique set of problems gets me out of bed every day and drives a high energy level. I have spent a significant amount of time in various aspects of operations engineering throughout my career, and have found this area of software engineering not always so readily accessible or accurately portrayed. In this post, I'll shed some light on the discipline.